© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115051
    Prev
    Next
    INDEX
    Explanations

    ensure things are done properly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surprisingly
    -0.14
     conceded
    -0.10
     reportedly
    -0.10
    ritel
    -0.10
     IGNORE
    -0.10
    agini
    -0.10
     much
    -0.10
     Whe
    -0.10
     remarkably
    -0.10
     strangely
    -0.10
    POSITIVE LOGITS
     properly
    0.19
     adequately
    0.17
     correctly
    0.15
     thoroughly
    0.14
     lest
    0.13
     sufficiently
    0.13
     adequate
    0.12
    æŃ£ç¡®
    0.12
     enough
    0.12
     remains
    0.12
    Activations Density 0.204%

    No Known Activations